<ul><li>FedC4 is a novel framework that combines graph condensation with client-client collaboration for efficient and private federated graph learning.</li><li>Existing methods in federated graph learning (FGL) can be categorized into the server-client (S-C) paradigm and the client-client (C-C) paradigm.</li><li>FedC4 distills each client's private graph into a compact set of synthetic node embeddings, reducing communication overhead and enhancing privacy.</li><li>Extensive experiments show that FedC4 outperforms state-of-the-art baselines in both performance and communication efficiency.</li></ul>

FedC4: Graph Condensation Meets Client-Client Collaboration for Efficient and Private Federated Graph Learning

Discover more